Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tool analysis knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాన్ని
    0.90
     sombre
    0.80
    vä
    0.80
     bhij
    0.79
     chirurg
    0.78
    ہرے
    0.78
    nica
    0.78
    𝙣
    0.77
     väx
    0.74
    mits
    0.74
    POSITIVE LOGITS
    дная
    1.07
    дный
    0.97
    дных
    0.91
    дные
    0.88
    дцать
    0.85
     दुश्
    0.83
    льным
    0.82
    か
    0.82
    ي
    0.81
     Poor
    0.81
    Act Density 0.000%

    No Known Activations